Deep least-squares methods: an unsupervised learning-based numerical method for solving elliptic PDEs
From MaRDI portal
Publication:2125011
DOI10.1016/j.jcp.2020.109707OpenAlexW2985622559WikidataQ114163498 ScholiaQ114163498MaRDI QIDQ2125011
Min Liu, Jingshuang Chen, Xin Yu Liu, Zhi-qiang Cai
Publication date: 11 April 2022
Published in: Journal of Computational Physics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1911.02109
Related Items (32)
Adaptive two-layer ReLU neural network. I: Best least-squares approximation ⋮ Adaptive two-layer ReLU neural network. II: Ritz approximation to elliptic PDEs ⋮ Least-squares ReLU neural network (LSNN) method for linear advection-reaction equation ⋮ SPINN: sparse, physics-based, and partially interpretable neural networks for PDEs ⋮ APFOS-Net: asymptotic preserving scheme for anisotropic elliptic equations with deep neural network ⋮ Self-adaptive deep neural network: numerical approximation to functions and PDEs ⋮ DeLISA: deep learning based iteration scheme approximation for solving PDEs ⋮ On quadrature rules for solving partial differential equations using neural networks ⋮ VPVnet: A Velocity-Pressure-Vorticity Neural Network Method for the Stokes’ Equations under Reduced Regularity ⋮ Least-squares ReLU neural network (LSNN) method for scalar nonlinear hyperbolic conservation law ⋮ A finite element based deep learning solver for parametric PDEs ⋮ Adaptive deep neural networks methods for high-dimensional partial differential equations ⋮ Towards fast weak adversarial training to solve high dimensional parabolic partial differential equations using XNODE-WAN ⋮ On computing the hyperparameter of extreme learning machines: algorithm and application to computational PDEs, and comparison with classical and high-order finite elements ⋮ DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method ⋮ A shallow Ritz method for elliptic problems with singular sources ⋮ A discontinuity capturing shallow neural network for elliptic interface problems ⋮ Randomized neural network with Petrov-Galerkin methods for solving linear and nonlinear partial differential equations ⋮ Physics-Informed Neural Networks for Solving Dynamic Two-Phase Interface Problems ⋮ A deep first-order system least squares method for solving elliptic PDEs ⋮ Physics-informed neural networks for approximating dynamic (hyperbolic) PDEs of second order in time: error analysis and algorithms ⋮ Deep Ritz method with adaptive quadrature for linear elasticity ⋮ A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology ⋮ \(r\)-adaptive deep learning method for solving partial differential equations ⋮ Neural Network Method for Integral Fractional Laplace Equations ⋮ Data-driven control of agent-based models: an equation/variable-free machine learning approach ⋮ Least-squares neural network (LSNN) method for scalar nonlinear hyperbolic conservation laws: discrete divergence operator ⋮ A priori error estimate of deep mixed residual method for elliptic PDEs ⋮ Error assessment of an adaptive finite elements -- neural networks method for an elliptic parametric PDE ⋮ Multi-scale fusion network: a new deep learning structure for elliptic interface problems ⋮ A non-gradient method for solving elliptic partial differential equations with deep neural networks ⋮ Tool path optimization of selective laser sintering processes using deep learning
Uses Software
Cites Work
- Region configurations for realizability of lattice piecewise-linear models.
- The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
- DGM: a deep learning algorithm for solving partial differential equations
- Error bounds for approximations with deep ReLU networks
- Neural‐network‐based approximations for solving partial differential equations
- First-Order System Least Squares for Second-Order Partial Differential Equations: Part I
This page was built for publication: Deep least-squares methods: an unsupervised learning-based numerical method for solving elliptic PDEs
